def get_date_time(self, news_row):
date_str = news_row.xpath(
'string((.//table//table//tr)[1]/td)').extract_first().strip()
date_time = utils.create_date_time_tzinfo(date_str,
self.tzinfo,
date_formats=['%d/%m/%Y'])
return date_time
def get_date_time(self, news_row):
news_col_list = news_row.xpath('./td')
date_str = news_col_list[0].xpath('string()').extract_first().strip()
date_time = utils.create_date_time_tzinfo(date_str,
self.tzinfo,
date_formats=['%d/%m/%y'])
return date_time
def get_date_time(self, news_row):
date_str = news_row.xpath('string((./td)[2]/span)').extract_first(
).strip().strip('[').strip(']')
if date_str:
date_time = utils.create_date_time_tzinfo(date_str, self.tzinfo)
return date_time
else:
raise Exception('Error: Date parsing error')
def get_date_time(self, news_row):
date_str = news_row.xpath(
'string(.//span[contains(@class, "date-display-single")])'
).extract_first().strip()
if date_str:
date_time = utils.create_date_time_tzinfo(date_str, self.tzinfo)
return date_time
else:
raise Exception('Error: Date parsing error')
def __init__(self):
super().__init__()
self.exchange = ExchangeParser()
# parameters
self.mkt_id = du.get_mkt_id(self.exchange.uptick_name)
self.pdfs_dir = utils.PDF_DIR + self.exchange.uptick_name + '/'
utils.create_pdf_dir(self.pdfs_dir)
# private
self.latest_date = utils.create_date_time_tzinfo(
'30 DEC 2017', self.exchange.tzinfo)
def get_date_time(self, news_row):
date_str = news_row.xpath('string(./a/span)').extract_first()
date_str_list = utils.filter_spaces(date_str)
date_str = ''
for s in date_str_list:
s = s.strip()
date_str += s + ' '
if date_str:
date_time = utils.create_date_time_tzinfo(date_str, self.tzinfo)
return date_time
else:
raise Exception('Error: Date parsing error')
def get_date_time(self, news_row):
date_str = news_row.xpath(
'string(.//span[contains(@class, "meta-item published-date")])'
).extract_first().strip()
if date_str:
import re
date_str = re.compile('[0-9/]+').findall(date_str)[0]
date_time = utils.create_date_time_tzinfo(date_str, self.tzinfo,
['%d/%m/%Y'])
return date_time
else:
raise Exception('Error: Date parsing error')
def get_date_time(self, news_row):
date_str = news_row.xpath('string(.//div[contains(@class, "article-date")])'
).extract_first().strip()
if date_str:
date_str = utils.filter_spaces(date_str)[0]
date_time = utils.create_date_time_tzinfo(
date_str,
self.tzinfo,
)
return date_time
else:
raise Exception('Error: Date parsing error')
def __init__(self):
super().__init__()
self.exchange = ExchangeParser()
# parameters
self.mkt_id = du.get_mkt_id(self.exchange.uptick_name)
# todo: change uptick_name to col_name
self.pdfs_dir = utils.PDF_DIR + self.exchange.col_name + '/'
utils.create_pdf_dir(self.pdfs_dir)
# private
# if self.exchange.is_multi_source_exchange:
self.latest_date = utils.create_date_time_tzinfo(
'30 DEC 2017', self.exchange.tzinfo)
def get_date_time(self, news_row):
date_str = news_row.xpath(
'string((./td)[1]/a)').extract_first().strip()
if date_str:
date_str_list = date_str.split('-')
if len(date_str_list) >= 4:
date_str = date_str_list[2].strip()
else:
date_str = date_str_list[-1].strip()
date_time = utils.create_date_time_tzinfo(date_str, self.tzinfo,
['%d%m%Y'])
return date_time
else:
raise Exception('Error: Date parsing error')
def get_date_time(self, news_row):
date_str = news_row.xpath(
'string(./div[contains(@class, "date")])').extract_first()
date_str_list = utils.filter_spaces(date_str)
date_str = ''
for s in date_str_list:
s = s.strip()
if s.lower() != 'date':
date_str += s
if date_str:
date_time = utils.create_date_time_tzinfo(date_str, self.tzinfo)
return date_time
else:
raise Exception('Error: Date parsing error')
def get_date_time(self, news_row):
date_str = news_row.xpath(
'string(div[contains(@class,"news-releases__section--date")])').extract(
)[0]
date_time = utils.create_date_time_tzinfo(date_str, self.tzinfo)
return date_time